An ultrasound image-based deep multi-scale texture network for liver fibrosis grading in patients with chronic HBV infection.
An ultrasound image-based deep multi-scale texture network for liver fibrosis grading in patients with chronic HBV infection.
复制标题
基于超声图像的深层多尺度纹理网络用于慢性乙型肝炎感染患者的肝纤维化分级
DOI：
10.1111/liv.14999
复制
发表时间：
2021-10
影响因子：
6.7
通讯作者：
Zheng, Min
中科院分区：
文献类型：
--
作者：
Ruan, Dongsheng;Shi, Yu;Jin, Linfeng;Yang, Qiao;Yu, Wenwen;Ren, Haotang;Zheng, Weiyang;Chen, Yongping;Zheng, Nenggan;Zheng, Min
对慢性肝病患者进行肝纤维化分期的评估至关重要。然而，由于超声图像质量不高，基于超声图像的肝纤维化无创诊断仍然是一个悬而未决的问题。本研究旨在研究基于深度学习的方法在超声图像中对多中心患者肝纤维化分期的诊断准确性。在这项研究中，我们提出了一种新的基于深度学习的方法，称为多尺度纹理网络（MSTNet），以评估肝纤维化，该方法从构建的图像金字塔补丁中提取多尺度纹理特征。通过与APRI、FIB-4、Forns和超声医师比较，研究其诊断准确性。收集了4家医院508例肝活检患者的资料。根据严重纤维化（≥F2）和肝硬化（F4）的受试者工作特征（ROC）曲线确定ROC曲线下面积（AUC）。验证组中≥F2和F4的MSTNet AUC（95%置信区间）分别为0.92（0.87 - 0.96）和0.89（0.83 - 0.95），显著优于APRI、FIB-4和Forns。在评估≥F2时，MSTNet的灵敏度和特异性（85.1%（74.5%-92.0%）和87.6%（78.0%-93.6%））优于3名超声医师。拟议的MSTNet是一种基于超声图像的方法，用于慢性HBV感染患者肝纤维化的无创分级。
The evaluation of the stage of liver fibrosis is essential in patients with chronic liver disease. However, due to the low quality of ultrasound images, the non‐invasive diagnosis of liver fibrosis based on ultrasound images is still an outstanding question. This study aimed to investigate the diagnostic accuracy of a deep learning‐based method in ultrasound images for liver fibrosis staging in multicentre patients. In this study, we proposed a novel deep learning‐based approach, named multi‐scale texture network (MSTNet), to assess liver fibrosis, which extracted multi‐scale texture features from constructed image pyramid patches. Its diagnostic accuracy was investigated by comparing it with APRI, FIB‐4, Forns and sonographers. Data of 508 patients who underwent liver biopsy were included from 4 hospitals. The area‐under‐the ROC curve (AUC) was determined by receiver operating characteristics (ROC) curves for significant fibrosis (≥F2) and cirrhosis (F4). The AUCs (95% confidence interval) of MSTNet were 0.92 (0.87‐0.96) for ≥F2 and 0.89 (0.83‐0.95) for F4 on the validation group, which significantly outperformed APRI, FIB‐4 and Forns. The sensitivity and specificity of MSTNet (85.1% (74.5%‐92.0%) and 87.6% (78.0%‐93.6%)) were better than those of three sonographers in assessing ≥F2. The proposed MSTNet is a promising ultrasound image‐based method for the non‐invasive grading of liver fibrosis in patients with chronic HBV infection.
登录
查看更多内容
影响因子：
5.6
作者：
Chin JL;Pavlides M;Moolla A;Ryan JD
通讯作者：
Ryan JD
影响因子：
29.4
作者：
Castéra, L;Vergniol, J;De Lédinghen, V
通讯作者：
De Lédinghen, V
影响因子：
4.3
作者：
Ferraioli, Giovanna;Tinelli, Carmine;Zaramella, Marco
通讯作者：
Zaramella, Marco
影响因子：
13.5
作者：
Ganne-Carrie, Nathahe;Ziol, Marianne;Beaugrand, Michel
通讯作者：
Beaugrand, Michel
影响因子：
10.6
作者：
Mojsilovic, A;Popovic, M;Krstic, M
通讯作者：
Krstic, M